© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 17675
    Prev
    Next
    INDEX
    Explanations

    adjectives expressing emotional states such as sadness, happiness, and disappointment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional responses related to happiness and sadness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.70
    irrel
    -0.65
    apons
    -0.63
     controlled
    -0.61
    ailability
    -0.61
    rawled
    -0.60
    perse
    -0.60
    è£
    -0.60
    arser
    -0.59
     tended
    -0.58
    POSITIVE LOGITS
    dy
    0.82
     saddened
    0.78
     congr
    0.67
     congratulate
    0.66
     Parish
    0.63
     councillors
    0.61
    wic
    0.60
    roud
    0.59
     Citizens
    0.59
     fortunate
    0.59
    Activations Density 0.147%

    No Known Activations